检索结果-南通市图书馆

Machine Vision Based Fish Cutting Point Prediction for Target Weight

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第4期75卷 2247-2263页

作者： Yonghun Jang Yeong-seok seo Department of Computer Engineering Yeungnam UniversityGyeongsan38541Korea

Food processing companies pursue the distribution of ingredientsthat were packaged according to a certain weight. Particularly, foods like fishare highly demanded and supplied. However, despite the high quantity offish to be supplied, most seafood processing companies have yet to installautomation equipment. Such absence of automation equipment for seafoodprocessing incurs a considerable cost regarding labor force, economy, andtime. Moreover, workers responsible for fish processing are exposed to risksbecause fish processing tasks require the use of dangerous tools, such aspower saws or knives. To solve these problems observed in the fish processingfield, this study proposed a fish cutting point prediction method based onAI machine vision and target weight. The proposed method performs threedimensional(3D) modeling of a fish’s form based on image processing techniquesand partitioned random sample consensus (RANSAC) and extracts 3Dfeature information. Then, it generates a neural network model for predictingfish cutting points according to the target weight by performing machinelearning of the extracted 3D feature information and measured weight *** study allows for the direct cutting of fish based on cutting pointspredicted by the proposed method. Subsequently, we compared the measuredweight of the cut pieces with the target weight. The comparison result verifiedthat the proposed method showed a mean error rate of approximately 3%.

关键词： Machine vision fish cutting weight prediction artificial intelligence deep learning image processing

Parametric Study on Design Parameters of Water-running Robot Based on Dynamic Simulation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Bionic Engineering 2018年第6期15卷 960-970页

作者： HyunGyu Kim Yanheng Liu TaeWon seo Max Planck Institute for Intelligent Systems Stuttgart 70565 Germany School of Mechanical Engineering Yeungnam University Gyeongsan 38541 Republic of Korea School of Mechanical Engineering Hanyang University Seou104 763 Republic of Korea

There are many design parameters to determine a performance of a robot. Especially, in the case of the mobile robots, they requirc complicated motion at various environments to get high performances. In this sense, the analysis of the design parameters is the most important work to design an efficient mobile robot. In this study, we analyze the design parameters for the water-running robot. From the parametric study, we find some solutions to improve the performances of the robot. We derive dynamic equations for the water-running motion, and do a sensitivity analysis to understand the relationships between the parameters （frequency of the leg, stiffness of torsional springs that connects multi frames and mass of frames） and the performance of the water-running motion such as running speed and pitching stability. We use an orthogonal array to make various combinations of the parameters, and to reduce the number of a simulation process. As results, we summarize some solutions to improve the water-running motion. We are expecting that this study is going to be used to design robots that are operated on the water.

关键词： bioinspired robot water-running motion multi-body system dynamic simulation analysis of design parameters sensitivity analysis

Reinforced CNN Forensic Discriminator to Detect Document Forgery by DCGAN

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第6期71卷 6039-6051页

作者： seo-young Lim Jeongho Cho Department of Electrical Engineering Soonchunhyang UniversityAsan31538Korea

Recently,the technology of digital image forgery based on a generative adversarial network(GAN)has considerably improved to the extent that it is difficult to distinguish it from the original image with the naked eye by compositing and editing a person’s face or a specific part with the original ***,much attention has been paid to digital image forgery as a social ***,document forgery through GANs can completely change the meaning and context in a document,and it is difficult to identify whether the document is forged or not,which is ***,few studies have been conducted on document forgery and new forgery-related attacks have emerged ***,in this study,we propose a novel convolutional neural network(CNN)forensic discriminator that can detect forged text or numeric images by GANs using CNNs,which have been widely used in image classification for many *** strengthen the detection performance of the proposed CNN forensic discriminator,CNN was trained after image preprocessing,including salt and pepper as well asGaussian ***,we performed CNN optimization to make existing CNN more suitable for forged text or numeric image detection,which have mainly focused on the discrimination of forged faces to *** test evaluation results using Hangul texts and numbers showed that the accuracy of forgery discrimination of the proposed method was significantly improved by 20%in Hangul texts and 5%in numbers compared with that of existing state-of-the-art methods,which proved the proposed model performance superiority and verified that it could be a useful tool in reducing crime potential.

关键词： Digital forensics CNN GAN discriminator image processing

Bandwidth-Efficient Transmission Method for User View-Oriented Video Services

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2020年第12期65卷 2571-2589页

作者： Minjae seo Jong-Ho Paik Department of Computer Seoul Women’s UniversitySeoul01797Korea Department of Software Convergence Seoul Women’s UniversitySeoul01797Korea

The trend in video viewing has been evolving beyond simply providing a multi-view ***,a function that allows selection and viewing of a clip from a multi-view service that captures a specific range or object has been *** particular,the free-view service is an extended concept of multi-view and provides a freer ***,since numerous videos and additional data are required for its construction,all of the clips constituting the content cannot be simultaneously *** certain clips are selected and provided to the *** the video is not the preferred video,change request is made,and a delay occurs during retransmission from the *** due to frequent re-requests degrade the overall quality of *** free-view services,selectively transmitting the video according to the user’s desired viewpoint and region of interest within the limited network of available videos is *** this study,we propose a method of screening and providing the correct video based on objects in the *** on the method of recognizing the object in each clip,we designed a method of setting its priority based on information about the object’s location for each *** the transmission and receiving process using this information,the selected video can be rapidly recognized and ***,we present a service system configuration method and propose video selection examples for free-view services.

关键词： Free-viewpoint video multi-view video coding scene change object co-detection transmission method

The Parametric Study on the Development of the Large-Scale Coherent Structures in a Mixing Layer

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Thermal Science 2002年第1期11卷 21-30页

作者： Taewon seo Yong-Kyoon Eom School of Mechanical Engineering Andong National University Andong Korea

The theoretical investigation of the role of three-dimensional large-scale coherent structures and their mutual interactions in a developing plane mixing layer subjected to external forcing is presented. Large-scale coherent structures are decomposed into 3 fundamental and 2 subharmoic wave modes. A parametric study is carried out examining effects of a multitude of initial conditions. It is found that the evolution of the forced three-dimensional shear layer and the associated local entrainment can be influenced greatly by the initial amplitudes and phases of the large-scale modes. The presence of three-dimensional modes may have a profound effect on shear layer growth when forced at amplitudes comparable or larger than those of the two-dimensional ones. This effect is more pronounced at low frequency. Nonlinear interactions between the fundamentals and subharmonics indicate that subharmonics of the most amplified frequency of the shear layer are usually produced during the early stages of flow development, while its harmonics are always produced far downstream, regardless of initial conditions. The results of this study provide useful parametric information for the control, through multi-mode forcing, of shear layers in practical applications, aiming at mixing and transport augmentation.

关键词： large-scale coherent structure nonlinear interaction free shear layer mixing entrainment.

Voltage-induced material removal mechanism of copper for electrochemical-mechanical polishing applications

在线全文

学校读者我要写书评

暂无评论

中国有色金属学会会刊：英文版 2009年第B9期19卷 262-265页

作者： Sang-Jun HAN Yong-Jin seo Nano-Information Material ＆ Device Laboratory Daebul University Chonnam 526-702 Korea School of Fusion Technology Daebul University Chonnam 526-702 Korea

The current-voltage (I-V) curves, such as linear sweep voltammetry (LSV) and cyclic voltammetry (CV), were employed to evaluate the effect of electrolyte concentration on the electrochemical reaction trend. From the I-V curve, the electrochemical states of active, passive, transient and trans-passive region could be characterized. And then, the mechanism of the process of voltage-induced material removal in electrochemical mechanical polishing (ECMP) of copper was investigated. Scanning electron microscopy (SEM) and energy dispersive spectroscopy (EDS) analyses were used to observe the surface profile. Finally, the oxidation and reduction processes of the Cu surface were monitored by the repetition of anodic and cathodic potential from cyclic voltammetry (CV) method in acid-and alkali-based electrolyte.

关键词：电化学机械抛光材料去除机理铜电极电压诱导线性扫描伏安法扫描电子显微镜循环伏安法

Rolling Stability Enhancement via Balancing Tail for a Water-running Robot

在线全文

学校读者我要写书评

暂无评论

Journal of Bionic Engineering 2015年第3期12卷 395-405页

作者： HyunGyu Kim Dong Gyu Lee TaeWon seo School of Mechanical Engineering Yeungnam University Gyeongsan 712-749 Republic of Korea

Running on water produces very energy-efficient and fast motion in water environments. Many studies have been performed to develop bio-inspired water-running robots. To achieve good performance, the lifting force is very important for a robot to be able to run on water. The loss of lifting force is associated with the rolling stability of the robot on water. The purpose of this study is to improve the rolling stability of a water-running robot through the periodic motion of a balancing tail. Kinematic analysis was performed to calculate the motions of the legs and the tail, and static analysis was performed to calculate the balancing effect of the tail motion. A numerical model was suggested to determine the dynamic performance of the robotic platform based on kinematic and static results. A simulation based on the numerical model was performed, and the results were compared with empirical data from a robot prototype. The simulation results are in good agreement with the experimental data in terms of rolling stability The lifting force has only a slight effect. The results of this study can be used as a guideline for designing a stable water-running robot.

关键词： water-running robot balancing tail rolling stability lifting force basilisk lizard

Vertically Integrated Electronics: New Opportunities from Emerging Materials and Devices

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Nano-Micro Letters 2022年第12期14卷 195-223页

作者： seongjae Kim Juhyung seo Junhwan Choi Hocheon Yoo Department of Electronic Engineering Gachon University1342 Seongnam-daeroSujeong-guSeongnamGyeonggi-do 13120Republic of Korea Center of Bio-Integrated Electronics Northwestern UniversityEvanstonIL 60208USA Querrey Simpson Institute for Bioelectronics Northwestern UniversityEvanstonIL 60208USA Present Address:Department of Chemical Engineering Dankook University152 Jukjeon-roSuji-guYonginGyeonggi-do 16890Republic of Korea

Vertical three-dimensional(3D)integration is a highly attractive strategy to integrate a large number of transistor devices per unit *** approach has emerged to accommodate the higher demand of data processing capability and to circumvent the scaling limitation.A huge number of research efforts have been attempted to demonstrate vertically stacked electronics in the last two *** this review,we revisit materials and devices for the vertically integrated electronics with an emphasis on the emerging semiconductor materials that can be processable by bottom-up fabrication methods,which are suitable for future flexible and wearable *** vertically stacked integrated circuits are reviewed based on the semiconductor materials:organic semiconductors,carbon nanotubes,metal oxide semiconductors,and atomically thin two-dimensional materials including transi-tion metal *** features,device performance,and fabrication methods for 3D integration of the transistor based on each semiconductor are ***,we highlight recent advances that can be important milestones in the vertically integrated elec-tronics including advanced integrated circuits,sensors,and display *** are remaining challenges to overcome;however,we believe that the vertical 3D integration based on emerging semiconductor materials and devices can be a promising strategy for future electronics.

关键词： Vertical stacking Three-dimensional integration Metal routing Via-hole Two-dimensional semiconductors

Link-Privacy Preserving Graph Embedding Data Publication with Adversarial Learning

在线全文

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2022年第2期27卷 244-256页

作者： Kainan Zhang Zhi Tian Zhipeng Cai Daehee seo the Department of Computer Science Georgia State UniversityAtlantaGA 30303USA the Department of Electrical and Computer Engineering George Mason UniversityFairfaxVA 22030USA the National Center of Excellence in Software Sangmyung UniversitySeoul 03016Republic of Korea

The inefficient utilization of ubiquitous graph data with combinatorial structures necessitates graph embedding methods,aiming at learning a continuous vector space for the graph,which is amenable to be adopted in traditional machine learning algorithms in favor of vector *** embedding methods build an important bridge between social network analysis and data analytics,as social networks naturally generate an unprecedented volume of graph data *** social network data not only brings benefit for public health,disaster response,commercial promotion,and many other applications,but also gives birth to threats that jeopardize each individual’s privacy and ***,most existing works in publishing social graph embedding data only focus on preserving social graph structure with less attention paid to the privacy issues inherited from social *** be specific,attackers can infer the presence of a sensitive relationship between two individuals by training a predictive model with the exposed social network *** this paper,we propose a novel link-privacy preserved graph embedding framework using adversarial learning,which can reduce adversary’s prediction accuracy on sensitive links,while persevering sufficient non-sensitive information,such as graph topology and node attributes in graph *** experiments are conducted to evaluate the proposed framework using ground truth social network datasets.

关键词： graph embedding privacy preservation adversarial learning